Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74250
    Prev
    Next
    INDEX
    Explanations

    Code/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hb
    -0.53
    hip
    -0.49
     Rabin
    -0.48
    AutoField
    -0.47
    x
    -0.46
     Bhai
    -0.44
     Star
    -0.43
    hia
    -0.43
    Star
    -0.43
    ix
    -0.42
    POSITIVE LOGITS
     propOrder
    0.78
     AssemblyTitle
    0.67
     transfieras
    0.63
     المعيارى
    0.62
    RenderAtEndOf
    0.60
    RotationOrder
    0.60
     Lure
    0.59
    quartered
    0.58
    Personensuche
    0.57
     eventdata
    0.56
    Activations Density 0.000%

    No Known Activations